Follow the Object: Curriculum Learning for Manipulation Tasks with Imagined Goals
원문 초록
Learning robot manipulation through deep reinforcement learning in environments with sparse rewards is a challenging task. In this paper we address this problem by introducing a notion of imaginary object goals. For a given manipulation task, the object of interest is first trained to reach a desired target position on its own, without being manipulated, through physically realistic simulations. The object policy is then leveraged to build a predictive model of plausible object trajectories providing the robot with a curriculum of incrementally more difficult object goals to reach during training. The proposed algorithm, Follow the Object (FO), has been evaluated on 7 MuJoCo environments requiring increasing degree of exploration, and has achieved higher success rates compared to alternative algorithms. In particularly challenging learning scenarios, e.g. where the object's initial and target positions are far apart, our approach can still learn a policy whereas competing methods currently fail.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Deep Reinforcement Learning with Gradient Eligibility Traces
Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control
Turning Sand to Gold: Recycling Data to Bridge On-Policy and Off-Policy Learning via Causal Bound
rQdia: Regularizing Q-Value Distributions With Image Augmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.